mlsanityData to 7 Oct 2026

GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning

arXiv 2505.23399 ↗First posted 29 May 2025cs.AIcited by 56

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6%, and still enhances strong models like GPT-4o by up to 2--3%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 36 of its 76 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

36 of 76 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Visual Reasoning and Multi-Agent Approach in Multimodal Large Language Models (MLLMs): Solving TSP and mTSP Combinatorial Challenges26 Jun
  2. 2024Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View27 May
  3. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  4. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language1 Apr

Other references · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2024Qwen2.5 Technical Reportcited by 4,713
  9. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  10. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
20 more
  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  4. 2024DeepSeek-V3 Technical Reportcited by 724
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  6. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  7. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  8. 2022Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understandingcited by 360
  9. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  10. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 235
  11. 2022A Survey of Vision-Language Pre-Trained Modelscited by 177
  12. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
  13. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 102
  14. 2020COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learningcited by 100
  15. 2022Learning in Mean Field Games: A Surveycited by 56
  16. 2023ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT modelscited by 41
  17. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 30
  18. 2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
  19. 2024DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metricscited by 13
  20. 2021Composing games into complex institutionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 42; 2026: 14.

56 papers.

Sort:

By area:

  1. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 70
  2. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  3. 2025CF-VLM:CounterFactual Vision-Language Fine-tuningcited by 57
  4. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  5. 2025LongCodeZip: Compress Long Context for Code Language Modelscited by 38
  6. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 34
  7. 2025DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-offcited by 33
  8. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 30
  9. 2025OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaborationcited by 29
  10. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 27
  11. 2026FastVMT: Eliminating Redundancy in Video Motion Transfercited by 23
  12. 2025Failure-Driven Workflow Refinementcited by 19
38 more
  1. 2025Top-Down Semantic Refinement for Image Captioningcited by 16
  2. 2025LastingBench: Defend Benchmarks Against Knowledge Leakagecited by 14
  3. 2025RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliabilitycited by 14
  4. 2025Cost-Effective Communication: An Auction-based Method for Language Agent Interactioncited by 14
  5. 20253DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scalecited by 12
  6. 2025CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoorcited by 11
  7. 2025FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Modelscited by 11
  8. 2026Group Editing: Edit Multiple Images in One Gocited by 11
  9. 2025STORM: Search-Guided Generative World Models for Robotic Manipulationcited by 7
  10. 2025RLAE: Reinforcement Learning-Assisted Ensemble for LLMscited by 6
  11. 2025CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generationcited by 4
  12. 2026GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflowscited by 4
  13. 2025HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolutioncited by 3
  14. 2025MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformercited by 3
  15. 2025Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agentscited by 3
  16. 2026SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planningcited by 3
  17. 2026ConSensus: Multi-Agent Collaboration for Multimodal Sensingcited by 3
  18. 2025GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extractioncited by 2
  19. 2025Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Modelscited by 2
  20. 2026ResWM: Residual-Action World Model for Visual RLcited by 2
  21. 2025Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimizationcited by 1
  22. 2025Large Language Models as Discounted Bayesian Filterscited by 1
  23. 2025Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correctioncited by 1
  24. 2025MoE-DiffuSeq: Enhancing Long-Document Diffusion Models with Sparse Attention and Mixture of Expertscited by 1
  25. 2026InstanceAnimator: Multi-Instance Sketch Video Colorizationcited by 1
  26. 2026Token-Budget Distillation: Transferring Full-Token Semantics to Compressed Video Vision-Language Modelscited by 1
  27. 2025Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignmentcited by 0
  28. 2025DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Losscited by 0
  29. 2025Guardian: Decoupling Exploration from Safety in Reinforcement Learningcited by 0
  30. 2025Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classificationcited by 0
  31. 2025GTMA: Dynamic Representation Optimization for OOD Vision-Language Modelscited by 0
  32. 2025PTTA: A Pure Text-to-Animation Framework for High-Quality Creationcited by 0
  33. 2025SirenPose: Dynamic Scene Reconstruction via Geometric Supervisioncited by 0
  34. 2025RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blockscited by 0
  35. 2025A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generationcited by 0
  36. 2025Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priorscited by 0
  37. 2025Towards Efficient Post-Training via Fourier-Driven Adapter Architecturescited by 0
  38. 2026DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protectioncited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use
  2. 2026Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
  3. 2026Collaborative Memory for Multi-Agent VLM Systems
  4. 2025Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
  5. 2025VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
  6. 2025Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
  7. 2026Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
  8. 2026MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning